Direct Preference Optimization for Neural Machine Translation with Minimum Bayes Risk Decoding

Minimum Bayes Risk (MBR) decoding can significantly improve translation performance of Multilingual Large Language Models (MLLMs). However, MBR decoding is computationally expensive and in this paper, we show how recently developed Reinforcement Learning (RL) technique, Direct Preference Optimization (DPO) can be used to fine-tune MLLMs so that we get the gains from MBR without the additional computation in inference. Our fine-tuned models have significantly improved performance on multiple NMT test sets compared to base MLLMs without preference optimization. Our method boosts the translation performance of MLLMs using relatively small monolingual fine-tuning sets.